Transformation of long-period stacking ordered structures in Mg-Gd-Y-Zn alloys upon synergistic characterization of first-principles calculation and experiment and its effects on mechanical properties

Based on experiments and first-principles calculations,the microstructures and mechanical properties of as-cast and solution treated Mg-10Gd-4Y-xZn-0.6Zr(x=0,1,2,wt.%)alloys are investigated.The transformation process of long-period stacking ordered(LPSO)structure during solidification and heat treatment and its effect on the mechanical properties of experimental alloys are discussed.Results reveal that the stacking faults and 18R LPSO phases appear in the as-cast Mg-10Gd-4Y-1Zn-0.6Zr and Mg-10Gd-4Y-2Zn-0.6Zr alloys,respectively.After solution treatment,the stacking faults and 18R LPSO phase transform into 14H LPSO phase.The Enthalpies of formation and reaction energy of 14H and 18R LPSO are calculated based on first-principles.Results show that the alloying ability of 18R is stronger than that of 14H.The reaction energies show that the 14H LPSO phase is more stable than the 18R LPSO.The elastic properties of the 14H and 18R LPSO phases are also evaluated by first-principles calculations,and the results are in good agreement with the experimental results.The precipitation of LPSO phase improves the tensile strength,yield strength and elongation of the alloy.After solution treatment,the Mg-10Gd-4Y-2Zn-0.6Zr alloy has the best mechanical properties,and its ultimate tensile strength and yield strength are 278.7 MPa and 196.4 MPa,respectively.The elongation of Mg-10Gd-4Y-2Zn-0.6Zr reaches 15.1,which is higher than that of Mg-10Gd-4Y0.6Zr alloy.The improving mechanism of elastic modulus by the LPSO phases and the influence on the alloy mechanical properties are also analyzed.

Locally Enhanced Flow and Electric Fields Through a Tip Effect for Efficient Flow‑Electrode Capacitive Deionization

Low-electrode capacitive deionization(FCDI)is an emerging desalination technology with great potential for removal and/or recycling ions from a range of waters.However,it still suffers from inefficient charge transfer and ion transport kinetics due to weak turbulence and low electric intensity in flow electrodes,both restricted by the current collectors.Herein,a new tip-array current collector(designated as T-CC)was developed to replace the conventional planar current collectors,which intensifies both the charge transfer and ion transport significantly.The effects of tip arrays on flow and electric fields were studied by both computational simulations and electrochemical impedance spectroscopy,which revealed the reduction of ion transport barrier,charge transport barrier and internal resistance.With the voltage increased from 1.0 to 1.5 and 2.0 V,the T-CC-based FCDI system(T-FCDI)exhibited average salt removal rates(ASRR)of 0.18,0.50,and 0.89μmol cm^(-2) min^(-1),respectively,which are 1.82,2.65,and 2.48 folds higher than that of the conventional serpentine current collectors,and 1.48,1.67,and 1.49 folds higher than that of the planar current collectors.Meanwhile,with the solid content in flow electrodes increased from 1 to 5 wt%,the ASRR for T-FCDI increased from 0.29 to 0.50μmol cm^(-2) min^(-1),which are 1.70 and 1.67 folds higher than that of the planar current collectors.Additionally,a salt removal efficiency of 99.89%was achieved with T-FCDI and the charge efficiency remained above 95%after 24 h of operation,thus showing its superior long-term stability.

Late effects of the treatment of childhood cancer

Excellent progress has been made in the last few decades in the cure rates of pediatric malignancies,with more than 80%of children with cancer who have access to contemporary treatment being cured.However,the therapies responsible for this survival can also produce adverse physical and psychological long-term outcomes,referred to as late effects,which appear months to years after the completion of cancer treatment.Research has shown that 60%to 90%of childhood cancer survivors(CCSs)develop one or more chronic health conditions,and 20%to 80%of survivors experience severe or life-threatening complications during adulthood.Therefore,understanding the late side effects of such treatments is important to improve the health and quality of life of the growing population of CCSs.

Novel Methodologies for Preventing Crack Propagation in Steel Gas Pipelines Considering the Temperature Effect

Using the software ANSYS-19.2/Explicit Dynamics,this study performedfinite-element modeling of the large-diameter steel pipeline cross-section for the Beineu-Bozoy-Shymkent gas pipeline with a non-through straight crack,strengthened by steel wire wrapping.The effects of the thread tensile force of the steel winding in the form of single rings at the crack edges and the wires with different winding diameters and pitches were also studied.The results showed that the strengthening was preferably executed at a minimum value of the thread tensile force,which was 6.4%more effective than that at its maximum value.The analysis of the influence of the winding dia-meters showed that the equivalent stresses increased by 32%from the beginning of the crack growth until the wire broke.The increment in winding diameter decelerated the disclosure of the edge crack and reduced its length by 8.2%.The analysis of the influence of the winding pitch showed that decreasing the distance between the winding turns also led to a 33.6%reduction in the length of the straight crack and a 7.9%reduction in the maximum stres-ses on the strengthened pipeline cross-section.The analysis of the temperature effect on the pipeline material,within a range from-40℃ to+50℃,resulted in a crack length change of up to 5.8%.As the temperature dropped,the crack length decreased.Within such a temperature range,the maximum stresses were observed along the cen-tral area of the crack,which were equal to 413 MPa at+50℃ and 440 MPa at-40℃.The results also showed that the presence of the steel winding in the pipeline significantly reduced the length of crack propagation up to 8.4 times,depending on the temperature effect and design parameters of prestressing.This work integrated the existing methods for crack localization along steel gas pipelines.

Relationship between parenting stress and behavioral and emotional problems in preschool children: A mediation effect analysis

BACKGROUND Emotional reactions,such as anxiety,irritability,and aggressive behavior,have attracted clinical attention as behavioral and emotional problems in preschool-age children.AIM To investigate the current status of family rearing,parental stress,and behavioral and emotional problems of preschool children and to analyze the mediating effect of the current status of family rearing on parental stress and behavioral/emo-tional problems.METHODS We use convenience sampling to select 258 preschool children in the physical examination center of our hospital from October 2021 to September 2023.The children and their parents were evaluated using a questionnaire survey.Pearson's correlation was used to analyze the correlation between child behavioral and emotional problems and parental stress and family rearing,and the structural equation model was constructed to test the mediating effect.RESULTS The score for behavioral/emotional problems of 258 preschool children was(27.54±3.63),the score for parental stress was(87.64±11.34),and the score for parental family rearing was(31.54±5.24).There was a positive correlation between the behavioral and emotional problems of the children and the“hostile/mandatory”parenting style;meanwhile,showed a negative correlation with the“support/participation”parenting style(all P<0.05).The intermediary effect value between the family upbringing of parents in parental stress and children's behavior problems was 29.89%.CONCLUSION Parental family upbringing has a mediating effect between parental stress and behavioral and emotional problems of children.Despite paying attention to the behavioral and emotional problems of preschool-age children,clinical medical staff should provide correct and reasonable parenting advice to their parents to promote the mental health of preschool-age children.

Variations in quantifying patient reported outcome measures to estimate treatment effect

In the practice of healthcare,patient-reported outcomes(PROs)and PRO measures(PROMs)are used as an attempt to observe the changes in complex clinical situations.They guide us in making decisions based on the evidence regarding patient care by recording the change in outcomes for a particular treatment to a given condition and finally to understand whether a patient will benefit from a particular treatment and to quantify the treatment effect.For any PROM to be usable in health care,we need it to be reliable,encapsulating the points of interest with the potential to detect any real change.Using structured outcome measures routinely in clinical practice helps the physician to understand the functional limitation of a patient that would otherwise not be clear in an office interview,and this allows the physician and patient to have a meaningful conver-sation as well as a customized plan for each patient.Having mentioned the rationale and the benefits of PROMs,understanding the quantification process is crucial before embarking on management decisions.A better interpretation of change needs to identify the treatment effect based on clinical relevance for a given condition.There are a multiple set of measurement indices to serve this effect and most of them are used interchangeably without clear demarcation on their differences.This article details the various quantification metrics used to evaluate the treatment effect using PROMs,their limitations and the scope of usage and implementation in clinical practice.

Effect of stacking fault energy on mechanical properties of ultrafine-grain Cu and Cu-Al alloy processed by cold-rolling

Cu,Cu-2.2%Al and Cu-4.5%Al with stacking fault energies（SFE） of 78,35 and 7 mJ/m2 respectively were processed by cold-rolling（CR） at liquid nitrogen temperature（77 K） after hot-rolling.X-ray diffraction measurements indicate that a decrease in SFE leads to a decrease in crystallite size but increase in microstrain,dislocation and twin densities of the CR processed samples.Tensile tests at room temperature indicate that as the stacking fault energy decreases,the strength and ductility increase.The results indicate that decreasing stacking fault energy is an optimum method to improve the ductility without loss of strength.

基于Stacking融合模型的Web攻击检测方法

随着计算机技术与互联网技术的飞速发展,Web应用在人们的生产与生活中扮演着越来越重要的角色。但是在人们的日常生活与工作中带来了更多便捷的同时,却也带来了严重的安全隐患。在开发Web应用的过程中,大量不规范的新技术应用引入了很多的网站漏洞。攻击者可以利用Web应用开发过程中的漏洞发起攻击,当Web应用受到攻击时会造成严重的数据泄露和财产损失等安全问题,因此Web安全问题一直受到学术界和工业界的关注。超文本传输协议(HTTP)是一种在Web应用中广泛使用的应用层协议。随着HTTP协议的大量使用,在HTTP请求数据中包含了大量的实际入侵,针对HTTP请求数据进行Web攻击检测的研究也开始逐渐被研究人员所重视。本文提出了一种基于Stacking融合模型的Web攻击检测方法,针对每一条文本格式的HTTP请求数据,首先进行格式化处理得到既定的格式,结合使用Word2Vec方法和TextCNN模型将其转换成向量化表示形式;然后利用Stacking模型融合方法,将不同的子模型(使用配置不同尺寸过滤器的Text-CNN模型搭配不同的检测算法)进行融合搭建出Web攻击检测模型,与融合之前单独的子模型相比在准确率、召回率、F1值上都有所提升。本文所提出的Web攻击检测模型在公开数据集和真实环境数据上都取得了更加稳定的检测性能。

基于Stacking融合模型的PHEV复合储能系统实时能量分配策略

为了解决插电式混合动力汽车单一电池低比功率、无法响应暂态功率需求的问题,设计了电池和超级电容并联式复合储能系统。同时针对采用动态规划法优化负载电流分配时缺乏实时性的问题,利用不同驱动工况下动态规划优化的结果构成训练集进行训练,并综合GRU网络以及XGBoost算法,提出了一种Stacking集成学习框架下多模型融合的能量分配策略。仿真结果表明,与仅使用单一电池的储能系统相比,基于Stacking融合模型的实时能量分配系统在UDDS和US06两种循环工况下,电池峰值电流分别降低了48.7%和50.8%,有效削弱了电池的峰值电流,提升了电池的整体性能。

基于Stacking集成学习的热轧带钢凸度诊断模型

在热连轧生产过程中,凸度是重要的质量指标,过程数据的非平衡性限制了数据驱动模型的预测效果,为提高模型的预测精度,提出一种融合SMOTE和Stacking集成算法的热轧带钢凸度诊断模型。首先,采用SMOTE过采样方法处理凸度相关数据集,降低数据非平衡分布导致的影响;然后,构建以轻量级梯度提升机(LightGBM)、支持向量机(SVM)、K近邻(KNN)和随机森林(RF)为基学习器,逻辑回归(LR)为元学习器的Stacking集成模型,最后,使用某2160 mm热轧带钢实际生产数据进行模型验证。研究结果表明,诊断模型的准确率、少数类召回率、平衡F分数、几何平均值和ROC曲线下面积分别为0.9580、0.9595、0.9573、0.9589和0.9579,与XGBoost、LightGBM、KNN、SVM和随机森林模型对比,预测效果最优,证明了Stacking集成算法能够有效增强诊断模型的泛化能力,具有优良的诊断性能。

近红外光谱结合Stacking集成学习的猕猴桃糖度检测研究

利用近红外光谱技术Stacking集成学习对猕猴桃糖度的无损检测。以湖北“云海一号”猕猴桃为研究对象,采用红外分析仪获取了280个样本的光谱数据,包含了4000~10000cm^(-1)范围内的1557个波长数据,使用折射仪测量糖度值。通过蒙特卡洛随机采样结合T检验的奇异样本识别算法筛除异常值样本。利用SPXY算法按照4∶1的比例划分训练集和测试集。使用多元散射校正(MSC)、SG平滑滤波(SG)、趋势校正(DT)、矢量归一化(VN)、标准正态变换(SNV)五种方法对数据进行预处理。使用无信息变量消除法(UVE)、竞争性自适应重加权算法(CARS)和区间变量迭代空间收缩特征选择算法(iVISSA)提取特征波长,使用连续投影算法(SPA)进行二次提取,消除共线性变量。由于单一模型的泛化能力有限,为了扩大建模能力,设计了一种基于Stacking算法的集成学习模型。选择贝叶斯岭回归(BRR)、偏最小二乘回归(PLSR)、支持向量机回归(SVR)以及人工神经网络(ANN)作为基学习器,线性回归(LR)作为元学习器建立集成模型,比较不同组合下集成模型的性能。使用Pearson相关系数分析基学习器与集成模型之间的关系。结果表明:在五种预处理方法之中,矢量归一化的效果最佳。对预处理后的光谱进行特征波长提取,结果显示VN-CARS-PLSR模型效果最好,在测试集上的RP2为0.805,RMSEP为0.498。模型提取了177个特征波长,数据量相比于原始光谱减少了88.6%。通过Stacking算法对基学习器进行融合,对比不同的组合方式,发现PLS+SVR+ANN集成模型预测精度最高,RP2达到了0.853,RMSEP下降至0.433。通过Pearson相关系数分析了基学习器对集成模型性能的影响。研究表明,与单一模型相比,Stacking集成模型能够进行更加全面的建模,具有更高的泛化能力,该方法为猕猴桃糖度品质的无损检测提供了技术支持。

基于组合时域特征提取和Stacking集成学习的燃煤锅炉NO_(x)排放浓度预测

为提高火电厂锅炉出口NO_(x)排放浓度的预测精度,提出一种考虑组合时域特征的Stacking集成学习模型。首先,为挖掘数据深层信息,采用时序分析、完全自适应噪声集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise analysis,CEEMDAN)和统计学计算数据标准差、偏度等特征的方法进行组合时域特征提取以构建重构数据;其次,考虑到重构数据中存在的冗余变量对模型的精度有所影响,利用遗传算法(genetic algorithm,GA)对重构数据进行特征降维;最后,为充分发挥各个模型的优势以提高模型的预测精度,构建以极限学习机(extreme learning machines,ELM)、深度神经网络(deep neural networks,DNN)、多层感知器(multilayer perceptron,MLP)、极限梯度提升算法(extreme gradient boosting,XGBoost)为基模型和以回声状态网络(echo state network,ESN)为元模型的Stacking集成学习NOx排放浓度预测模型。实验结果表明:该预测模型在不同数据集下都有着不错的预测效果,预测误差均小于2%,能够对锅炉NOx排放浓度实现精准预测。

基于FIR-Stacking的刀具磨损预测

针对铣刀加工工件时传感器信号存在噪声、单一传统机器学习模型预测效果不理想的问题,提出一种基于自适应FIR滤波器和Stacking集成模型的刀具磨损预测方法。首先,采用自适应FIR滤波器去噪,计算时域、频域和时频域常用统计量作为信号特征,并对同一信号的多源信号特征进行拼接,经Pearson相关系数筛选保留相关系数大于0.2的特征;最后,以LightGBM、支持向量回归(support vector regression,SVR)、多层感知机(multilayer perceptron,MLP)作为基模型,Lasso作为元模型,构建Stacking集成模型进行刀具磨损预测。使用铣削加工数据集进行验证,结果表明该方法可有效提高预测准确性。

基于Stacking算法集成学习的页岩油储层总有机碳含量评价方法

总有机碳含量(TOC)是页岩油储层评价的重要参数,而传统总有机碳含量测井评价方法精度较低且普适性较差,机器学习模型在一定程度上提高了总有机碳含量预测精度,但结果存在不稳定性。为了进一步提高页岩油储层总有机碳含量预测精度,基于有机质岩石物理特征和不同总有机碳含量测井响应特征的深入分析,优选出深侧向电阻率、声波时差、补偿中子和密度测井曲线作为总有机碳含量的敏感测井响应,并将其作为输入特征,以岩心分析总有机碳含量作为期望输出值,分别建立了决策树模型、支持向量回归机模型、BP(Back Propagation)神经网络模型,并建立了以决策树模型为基模型、支持向量回归机模型为元模型的Stacking算法集成学习模型。利用B油田A区块的岩心样本数据和实际井数据对不同模型预测总有机碳含量结果进行了验证,结果表明,基于Stacking算法的集成学习模型的总有机碳含量预测精度最高,相较于决策树模型、支持向量回归机模型、BP神经网络模型和改进的ΔlgR法,预测精度有较大提高。因此,基于Stacking算法的集成学习模型为该研究区最有效的总有机碳含量计算方法,这为准确地评估页岩油储层的生烃潜力、确保页岩油储层的高效开采及资源利用奠定了基础。

基于Stacking集成学习的声波时差测井曲线复原研究

声波时差测井曲线在石油勘探中发挥着不可或缺的作用,但是受地质或仪器的影响,经常会出现部分甚至完整的声波测井曲线缺失的情况。针对这一问题,提出了一种基于Stacking集成学习的声波时差测井曲线复原方法,该模型使用随机森林(RF)、梯度提升决策树(GBDT)、轻量梯度提升机(LightGBM)和极限梯度提升(XGBoost)作为基学习器,支持向量回归(SVR)作为元学习器,同时采用5折交叉验证的方法。实验选取了大庆油田某区块的实际测井数据,分别进行了同井和异井间的缺失声波时差测井曲线复原实验,结果表明,所提方法比单一模型预测更加准确,验证了此方法的可行性。

基于Stacking集成算法的抛石护岸水毁破坏预测研究

抛石护岸在顶冲等极端情况下易发生水毁破坏,给人民的生命财产带来威胁。通过水槽试验获取496组样本数据,利用互信息(MI)筛选出6个关键特征属性,并采用支持向量机(SVR)、广义回归神经网络(GRNN)和随机森林(RF)等机器学习算法构建多个预测模型。然后,将这些模型作为基学习器,结合BP神经网络(BPNN)作为元学习器,采用Stacking集成学习方法构建抛石护岸破坏程度预测模型。最后,通过决定系数(R^(2))、均方根误差(R_(RMSE))及平均绝对误差(M_(MAE))等评价指标对模型性能进行评估。结果表明,Stacking模型在抛石护岸破坏高度、长度、范围上的平均R^(2)为0.98、RRMSE为0.02、M_(MAE)为0.03,相较于单一模型(SVR、GRNN、RF),Stacking模型的R_(RMSE)、M_(MAE)皆为最小,R2最高。在抛石护岸水毁破坏程度的预测中,融合的Stacking模型展现出更高的准确性与稳定性。

基于Stacking模型的学术论文多标签分类系统构建

学术论文高质量多标签自动分类是推动学术研究发展的关键程序之一。本研究利用Stacking模型将随机森林、支持向量机、极限树、极端梯度提升和神经网络五个分类器融合为一个异质集成分类器,并利用基于问题转换思想的多二分类模型将该分类器应用于学术论文多标签分类。根据学术论文的特点,依次实现了与之配套的论文特征提取模块、TF-IDF加权模块、数据预处理模块,最终构建成一个面向学术论文的多标签分类系统。仿真实验验证了本研究构建的学术论文多标签分类系统在处理学术论文多标签分类问题时,较传统的单模型分类器或同质集成模型分类器在泛化能力、稳定性与准确率方面都有一定程度的提升。图9。参考文献21。

基于互补集成经验模态分解和Stacking融合的短期风速组合预测模型

针对风电场短期风速预测准确度不高的问题,提出一种基于互补集成经验模态分解和Stacking融合的短期风速组合预测模型。首先,为突出短期风速的局部特征并降低建模难度,通过互补集成经验模态分解算法将短期风速分解为若干个稳定分量。然后,利用信息熵和近似熵来判定各分量的复杂度,高复杂度分量选择最小二乘支持向量机、低复杂度分量选择随机配置网络作为对应的预测模型。利用Stacking算法对每个模型的预测值进行融合,使预测精度得到提升。最后,通过一组实际的短期风速数据作为研究对象,将提出的预测模型应用于其预测。对比结果表明,所提预测模型可提高短期风速的预测精度。

基于VMD-Stacking集成学习的新能源发电功率预测模型

在“双碳”背景下,新能源发电功率的准确预测对于电力系统的平稳运行至关重要。提出了一种自适应性的VMD-Stacking集成模型,以解决数据集变化时传统学习模型预测精度不高的问题。利用皮尔逊相关系数选择与发电功率强相关的气象特征,通过变分模态分解(Variational mode decomposition,VMD)将功率数据分解为多个模态分量,由此构成新的数据集。运用贝叶斯优化算法调整超参数,综合评判随机森林等8种学习模型的评价指标,自适应选出预测性能最优的3种模型作为基学习器,并选用稳定性和泛化能力相对较强的线性回归(Linear Regression)作为元学习器,建立Stacking融合模型。对各分量的预测值叠加,得到最终预测结果。以某新能源场站为例,对风、光电站的发电功率进行预测。算例验证结果表明,该模型在面对不同数据集时,体现出较强的适应性,预测性能也得到显著的提升。

基于Stacking融合的LSTM-SA-RBF短期负荷预测

为了解决单个神经网络预测的局限性和时间序列的波动性,提出了一种奇异谱分析(singular spectrum analysis,SSA)和Stacking框架相结合的短期负荷预测方法。利用随机森林筛选出与历史负荷相关性强烈的特征因素,采用SSA为负荷数据降噪,简化模型计算过程;基于Stacking框架,结合长短期记忆(long and short-term memory,LSTM)-自注意力机制(self-attention mechanism,SA)、径向基(radial base functions,RBF)神经网络和线性回归方法集成新的组合模型,同时利用交叉验证方法避免模型过拟合;选取PJM和澳大利亚电力负荷数据集进行验证。仿真结果表明,与其他模型比较,所提模型预测精度高。